Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    protection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    úng
    -0.09
     Kathmandu
    -0.08
     دینے
    -0.08
    ðin
    -0.08
     �
    -0.08
    šie
    -0.08
    šem
    -0.08
    tops
    -0.08
     seamless
    -0.08
     Recre
    -0.08
    POSITIVE LOGITS
     conspiracy
    0.10
     consent
    0.10
     confidentialité
    0.09
     GDPR
    0.09
     privacy
    0.09
    Consent
    0.09
     confidentiality
    0.08
     conformité
    0.08
    RFC
    0.08
     obowią
    0.08
    Act Density 0.010%

    No Known Activations